Supplementary Materials for "Beyond grades: multi-target deep learning for early academic risk detection"

This repository contains the supplementary materials associated with the article:

“Beyond grades: multi-target deep learning for early academic risk detection”

The materials support the robustness, interpretability, reproducibility, and pedagogical analysis of the proposed multi-output deep learning framework for early academic risk detection in higher education.

Contents:

Supplementary Appendix A:
Dataset variables and feature definitions derived from institutional LMS and online assessment systems.

Supplementary Appendix B:
Additional methodological details, hyperparameter optimization settings, robustness analyses, and supplementary evaluation metrics.

Supplementary Appendix C:
Extended SHAP interpretability visualizations, predicted-versus-actual analyses, and behavioral clustering results related to self-regulated learning and formative assessment.

These materials complement the main manuscript and provide additional transparency and reproducibility for the reported findings.